Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.7662. Min Act: -0.1700
Data Index: 5017388 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6099. Min Act: -0.1700
Data Index: 8727789 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4849. Min Act: -0.1700
Data Index: 3896391 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 6412490 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 6775329 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 7047786 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 296793 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 2922337 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3912. Min Act: -0.1700
Data Index: 1956559 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3599. Min Act: -0.1700
Data Index: 1255172 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3287. Min Act: -0.1700
Data Index: 832099 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2974. Min Act: -0.1700
Data Index: 7887680 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3287. Min Act: -0.1700
Data Index: 2632863 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2974. Min Act: -0.1700
Data Index: 7516958 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2974. Min Act: -0.1700
Data Index: 4990625 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2974. Min Act: -0.1700
Data Index: 6484646 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2662. Min Act: -0.1700
Data Index: 832098 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2349. Min Act: -0.1700
Data Index: 5177197 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2349. Min Act: -0.1700
Data Index: 3468380 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.2037. Min Act: -0.1700
Data Index: 6316778 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19